This paper presents a path planner for Unmanned Air Vehicles (UAVs) based on Evolutionary Algorithms (EA) that can be used in realistic risky scenarios. The path returned by the algorithm fulfills and optimizes multiple criteria which (1) are calculated based on properties of real UAVs, terrains, radars and missiles, and (2) are used to rank the solutions according to the priority levels and goals selected for each mission. Developed originally to work with only one UAV, the planner currently allows us to obtain the optimal path of several UAVs that are flying simultaneously. It works globally offline and locally online to recalculate a part of the path when an unexpected threat appears. Finally, the effectiveness of the solutions given by this planner has been successfully tested against a simulator that implements a complex model of the UAV and its environment.

No abstract